Llama 3.3 70B Instruct Turbo
Llama-3.3-70B-Instruct-TurboPricing
List prices at DeepInfra, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.10 | $0.32 |
What it costs a month
At DeepInfra list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$54.00
- RAG over documents2,000 requests a day, 8K in / 0.6K out$59.52
- Coding agent1,000 requests a day, 40K in / 2K out$139
- Overnight batch20,000 requests a day, 4K in / 0.4K out$317
Where to run it
3 hosts serve Llama 3.3 70B Instruct Turbo. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
DeepInfraInference Llama-3.3-70B-Instruct-Turbo | $0.10 / $0.32 | Llama-3.3-70B-Instruct-Turbo | |
Inference APIsGateway Llama-3.3-70B-Instruct-Turbo | $0.20 / $0.50 +77% vs headline | Llama-3.3-70B-Instruct-Turbo | |
Together AIInference Llama-3.3-70B-Instruct-Turbo | $1.04 / $1.04 +571% vs headline | Llama-3.3-70B-Instruct-Turbo |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Open weights
- License: Llama Community LicenseRuntimes: Ollama, TGI, llama.cpp, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than DeepInfra.
Smaller Meta models
- 19% less
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 3% less
- 8% less
- 10% less
- 11% less
Call it
Using DeepInfra's API.
from litellm import completion
response = completion(
model="deepinfra/Llama-3.3-70B-Instruct-Turbo",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Llama 3.3 70B Instruct Turbo cost?
On DeepInfra, Llama 3.3 70B Instruct Turbo costs $0.10 per million input tokens and $0.32 per million output tokens.
Which APIs offer Llama 3.3 70B Instruct Turbo?
Llama 3.3 70B Instruct Turbo runs on 3 APIs: DeepInfra, Inference APIs and Together AI.
What is Llama 3.3 70B Instruct Turbo's context window?
131K tokens, with up to 131K tokens in one reply.
Is Llama 3.3 70B Instruct Turbo being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Llama 3.3 70B Instruct Turbo?
Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (19% less) and Ministral 8B 2512 on Mistral AI (3% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Llama 3.3 70B Instruct Turbo's API model id?
Use Llama-3.3-70B-Instruct-Turbo with DeepInfra.
Sources
Raw catalog entry for Llama-3.3-70B-Instruct-Turbo on DeepInfra
{
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 1e-7,
"output_cost_per_token": 3.2e-7,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"source": "https://deepinfra.com/pricing"
}